Mnist works at the moment with trt8,others like yolo4tiny and mobilenet generate the engine files but crash after throwing nvifer1::CudaRuntimeError and when demo is being run ,it doesnt deserialize properly and crashes

include/tkDNN/DarknetParser.h

@@ -47,5 +47,8 @@ namespace tk { namespace dnn {
                          std::vector<tk::dnn::Layer*> &netLayers, const std::vector<std::string>& names);
     std::vector<std::string> darknetReadNames(const std::string& names_file);
     tk::dnn::Network* darknetParser(const std::string& cfg_file, const std::string& wgs_path, const std::string& names_file);
+    void loadYoloInfo(const std::string &cfg_file,int lineNo,std::vector<float> &mask,std::vector<float> &anchors,int &num,int &classes,float &nms_thresh,int &nms_kind,int &coords);
+    void loadYoloInitInfo(int &channels,int &width,int &height,const std::string &cfg_file);
+    std::vector<int> noYolosLine(const std::string &cfg_file);
 
 }}

include/tkDNN/DetectionNN.h

@@ -87,7 +87,7 @@ class DetectionNN {
          * @param n_batches maximum number of batches to use in inference
          * @return true if everything is correct, false otherwise.
          */
-        virtual bool init(const std::string& tensor_path, const int n_classes=80, const int n_batches=1, const float conf_thresh=0.3) = 0;
+        virtual bool init(const std::string& tensor_path,const std::string& cfg_path,const std::string& name_path, const int n_classes=80, const int n_batches=1, const float conf_thresh=0.3) = 0;
         
         /**
          * This method performs the whole detection of the NN.

include/tkDNN/NetworkRT.h

@@ -7,6 +7,7 @@
 #include "Layer.h"
 #include "NvInfer.h"
 #include <memory>
+#include <tkDNN/kernels.h>
 
 namespace tk { namespace dnn {
 
@@ -52,7 +53,6 @@ public:
 
 
 
-
 class NetworkRT {
 
 public:

include/tkDNN/Yolo3Detection.h

@@ -4,9 +4,9 @@
 #include "opencv2/opencv.hpp"
 
 #include "DetectionNN.h"
+#include "DarknetParser.h"
 
-namespace tk { namespace dnn { 
-
+namespace tk { namespace dnn {
 class Yolo3Detection : public DetectionNN
 {
 private:
@@ -19,12 +19,13 @@ private:
     tk::dnn::Yolo* getYoloLayer(int n=0);
 
     cv::Mat bgr_h;
+    std::vector<int> noYolos;
     
 public:
     Yolo3Detection() {};
     ~Yolo3Detection() {}; 
 
-    bool init(const std::string& tensor_path, const int n_classes=80, const int n_batches=1, const float conf_thresh=0.3);
+    bool init(const std::string& tensor_path,const std::string& cfg_path,const std::string& name_path,const int n_classes=80, const int n_batches=1, const float conf_thresh=0.3);
     void preprocess(cv::Mat &frame, const int bi=0);
     void postprocess(const int bi=0,const bool mAP=false);
 };

include/tkDNN/pluginsRT/ReorgRT.h

@@ -41,7 +41,7 @@ public:
 
 	virtual int enqueue(int batchSize, const void*const * inputs, void* const* outputs, void* workspace, cudaStream_t stream) NOEXCEPT override {
 
-		reorgForward((dnnType*)reinterpret_cast<const dnnType*>(inputs[0]), 
+		reorgForward((dnnType*)reinterpret_cast<const dnnType*>(inputs[0]),
 					  reinterpret_cast<dnnType*>(outputs[0]), 
 					  batchSize, c, h, w, stride, stream);
 		return 0;

include/tkDNN/pluginsRT/YoloRT.h

@@ -31,6 +31,7 @@ public:
         classes = readBUF<int>(buf);
         num = readBUF<int>(buf);
         n_masks = readBUF<int>(buf);
+        std::cout<<n_masks<<std::endl;
         scaleXY = readBUF<float>(buf);
         nms_thresh = readBUF<float>(buf);
         nms_kind = readBUF<int>(buf);